# Improving Neural Networks for Time Series Forecasting using Data Augmentation and AutoML

arXiv: https://arxiv.org/abs/2103.01992 · HTML: https://mlsanity.com/paper/2103.01992/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 49 references that are in the map.
- First posted on arXiv 2 Mar 2021.

## Builds on (most cited first, 15 of 15)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Sequence to Sequence Learning with Neural Networks](https://mlsanity.com/paper/1409.3215/) (2014)
- [Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcasting](https://mlsanity.com/paper/1506.04214/) (2015)
- [Temporal Fusion Transformers for Interpretable Multi-horizon Time Series Forecasting](https://mlsanity.com/paper/1912.09363/) (2019)
- [Enhancing the Locality and Breaking the Memory Bottleneck of Transformer on Time Series Forecasting](https://mlsanity.com/paper/1907.00235/) (2019)
- [AutoML: A Survey of the State-of-the-Art](https://mlsanity.com/paper/1908.00709/) (2019)
- [A Dual-Stage Attention-Based Recurrent Neural Network for Time Series Prediction](https://mlsanity.com/paper/1704.02971/) (2017)
- [Recurrent Neural Networks for Time Series Forecasting: Current Status and Future Directions](https://mlsanity.com/paper/1909.00590/) (2019)
- [Auto-Keras: An Efficient Neural Architecture Search System](https://mlsanity.com/paper/1806.10282/) (2018)
- [Conditional Time Series Forecasting with Convolutional Neural Networks](https://mlsanity.com/paper/1703.04691/) (2017)
- [Deep Factors for Forecasting](https://mlsanity.com/paper/1905.12417/) (2019)
- [Video Contents Understanding using Deep Neural Networks](https://mlsanity.com/paper/2004.13959/) (2020)
- [Stereotype-Free Classification of Fictitious Faces](https://mlsanity.com/paper/2005.02157/) (2020)
- [Gaussian Function On Response Surface Estimation](https://mlsanity.com/paper/2101.00772/) (2021)
- [Occupancy Detection in Room Using Sensor Data](https://mlsanity.com/paper/2101.03616/) (2021)

## Built on by (most cited first, 7 of 7)

- [AutoGluon-TimeSeries: AutoML for Probabilistic Time Series Forecasting](https://mlsanity.com/paper/2308.05566/) (2023)
- [A Survey of Deep Learning and Foundation Models for Time Series Forecasting](https://mlsanity.com/paper/2401.13912/) (2024)
- [Efficient Automated Deep Learning for Time Series Forecasting](https://mlsanity.com/paper/2205.05511/) (2022)
- [Data Augmentation for Multivariate Time Series Classification: An Experimental Study](https://mlsanity.com/paper/2406.06518/) (2024)
- [Big Dataunicodex2013Supply Chain Management Framework for Forecasting: Data Preprocessing and Machine Learning Techniques](https://mlsanity.com/paper/2307.12971/) (2023)
- [Improving COVID-19 Forecasting using eXogenous Variables](https://mlsanity.com/paper/2107.10397/) (2021)
- [Adapt Data to Model: Adaptive Transformation Optimization for Domain-shared Time Series Foundation Models](https://mlsanity.com/paper/2603.00629/) (2026)

## Abstract (arXiv)

Statistical methods such as the Box-Jenkins method for time-series forecasting have been prominent since their development in 1970. Many researchers rely on such models as they can be efficiently estimated and also provide interpretability. However, advances in machine learning research indicate that neural networks can be powerful data modeling techniques, as they can give higher accuracy for a plethora of learning problems and datasets. In the past, they have been tried on time-series forecasting as well, but their overall results have not been significantly better than the statistical models especially for intermediate length times series data. Their modeling capacities are limited in cases where enough data may not be available to estimate the large number of parameters that these non-linear models require. This paper presents an easy to implement data augmentation method to significantly improve the performance of such networks. Our method, Augmented-Neural-Network, which involves using forecasts from statistical models, can help unlock the power of neural networks on intermediate length time-series and produces competitive results. It shows that data augmentation, when paired with Automated Machine Learning techniques such as Neural Architecture Search, can help to find the best neural architecture for a given time-series. Using the combination of these, demonstrates significant enhancement in the forecasting accuracy of three neural network-based models for a COVID-19 dataset, with a maximum improvement in forecasting accuracy by 21.41%, 24.29%, and 16.42%, respectively, over the neural networks that do not use augmented data.